Ol99zoW31J / logbook.json
DineshAI's picture
Claim 4 (Thm 11): test variance bound with expressive deep MLP policies (up to 5089 params)
504e723 verified
Raw
History Blame Contribute Delete
1.64 kB
{
"schema_version": 1,
"title": "Repro - Non-Uniform Noise-to-Signal Ratio in the REINFORCE Policy-Gradient Estimator (Ol99zoW31J)",
"emoji": "\ud83c\udfaf",
"space_id": "DineshAI/Ol99zoW31J",
"paper": null,
"tags": [
"icml2026-repro",
"paper-Ol99zoW31J"
],
"updated_at": "2026-07-22T04:22:00+00:00",
"root": {
"slug": "index",
"title": "Repro - Non-Uniform Noise-to-Signal Ratio in the REINFORCE Policy-Gradient Estimator (Ol99zoW31J)",
"file": "pages/index.md",
"children": [
{
"slug": "overview",
"title": "Overview",
"file": "pages/overview/page.md",
"children": []
},
{
"slug": "claim-1",
"title": "Claim 1",
"file": "pages/claim-1/page.md",
"children": []
},
{
"slug": "claim-2",
"title": "Claim 2",
"file": "pages/claim-2/page.md",
"children": []
},
{
"slug": "claim-3",
"title": "Claim 3",
"file": "pages/claim-3/page.md",
"children": []
},
{
"slug": "claim-4",
"title": "Claim 4",
"file": "pages/claim-4/page.md",
"children": []
},
{
"slug": "claim-5",
"title": "Claim 5",
"file": "pages/claim-5/page.md",
"children": []
},
{
"slug": "methods",
"title": "Methods",
"file": "pages/methods/page.md",
"children": []
},
{
"slug": "negative-controls",
"title": "Negative controls",
"file": "pages/negative-controls/page.md",
"children": []
},
{
"slug": "conclusion",
"title": "Conclusion",
"file": "pages/conclusion/page.md",
"children": []
}
]
},
"agent_view_tokens": 1514,
"revision": 1784562681057320335
}